andharsm/qwen2-5-1-5b-indonesian-sft-qlora-exp1

TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:May 31, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The andharsm/qwen2-5-1-5b-indonesian-sft-qlora-exp1 model is a 1.5 billion parameter Qwen2.5-based language model, fine-tuned by andharsm. This model was specifically trained using Unsloth and Huggingface's TRL library for accelerated performance. It is optimized for tasks requiring an instruction-tuned model, leveraging its Qwen2.5 architecture for efficient processing.

Loading preview...

Model Overview

This model, andharsm/qwen2-5-1-5b-indonesian-sft-qlora-exp1, is a 1.5 billion parameter language model developed by andharsm. It is fine-tuned from the unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit base model, indicating its foundation in the Qwen2.5 architecture and its instruction-tuned nature.

Key Characteristics

  • Base Model: Fine-tuned from unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit.
  • Training Efficiency: The fine-tuning process was accelerated using Unsloth and Huggingface's TRL library, enabling faster training times.
  • Parameter Count: Features 1.5 billion parameters, offering a balance between performance and computational efficiency.

Intended Use

This model is suitable for applications requiring an instruction-tuned language model, particularly benefiting from its efficient training methodology. Its Qwen2.5 foundation suggests capabilities in general language understanding and generation tasks.